AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning

Jiayao Mai, Bangyan Liao, Zhenjun Zhao, Yingping Zeng, Haoang Li, Javier Civera, Tailin Wu, Yi Zhou, Peidong Liu

ICLR 2026 · Reinforcement learning › Visual and representation RL · approach: RL with tree search for discovery · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Add NPC learned policy to GNCClassic GNC · GNC point cloud registration (bunny)corrector iterations: 783 -> 169Improved
Add NPC learned policy to GNCClassic GNC · GNC point cloud registration (cube)runtime (ms): 89.34 -> 7.86Improved
Add NPC to GNCClassic GNC · GNC point cloud registrationaccuracy: -1.12 -> -1.11No clear effect
Add NPC to GNCClassic GNC · GNC multi-view triangulation (reichstag)corrector iterations: 142 -> 21Improved
Add NPC to GNCClassic GNC · GNC multi-view triangulation (sacre_coeur)log10 point error: -5.15 -> -4.84Hurt
Add NPC to Gaussian homotopyClassic GH · GH 2d Ackleycorrector iterations: 501 -> 359Improved
Add NPC to Gaussian homotopyClassic GH · GH Himmelblauf(x*): 0.00 -> 0.00No clear effect
Add NPC to homotopy continuationClassic HC · HC katsura10corrector iterations: 39 -> 7Improved
Add NPC to homotopy continuationClassic HC · HC UPnPcorrector iterations: 53 -> 29Improved
Add NPC to annealed Langevin dynamicsClassic ALD · ALD 40-mode GMMcorrector iterations: 410 -> 110Improved
Add NPC to annealed Langevin dynamicsClassic ALD · ALD 40-mode GMMWasserstein-2: 11.57 -> 11.91No clear effect
Add NPC to Gaussian homotopy on 10d AckleyClassic GH · GH 10d Ackleyf(x*): 0.01 -> 0.47Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy